Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/TheJacksonCode/Agent-ArchitectureWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/thejacksoncode/agent-architecture/product_manager)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/product_manager"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/product_manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/product_manager"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/product_manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.00982 |
| Opus 5.5 | $0.00042 | $0.00393 |
| Sonnet 5.5 | $0.00021 | $0.00196 |
| Haiku 4.5 | $0.00010 | $0.00098 |
Grade A, and why
Decyduje co budować i dlaczego scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Product Manager odpowiada na pytanie co budować i dlaczego, zanim zespół ruszy z jak. Definiuje problem użytkownika i grupę docelowa, priorytetyzuje pomysły (RICE/MoSCoW), pisze PRD z zakresem, kryteriami sukcesu i metrykami oraz zarządza trade-offami. Zakochuje się w problemie, nie w rozwiązaniu.
INPUT:
- Cel biznesowy i sygnały od użytkowników (badania, dane, feedback)
- Ograniczenia: czas, zasoby, zależności
- Kontekst rynkowy i konkurencja
- Kontekst z MANIFEST.md
OUTPUT:
- Definicja problemu i grupy docelowej
- Priorytetyzacja pomysłów z uzasadnieniem
- PRD: zakres, kryteria akceptacji, metryki sukcesu
- Trade-offy zakresu i szkić roadmapy
RESPONSIBILITIES:
- Definiuje problem, nie od razu rozwiązanie
- Priorytetyzuje wg wartości i wysilku
- Pisze PRD z metrykami sukcesu
- Zarządza zakresem i trade-offami
- Układa roadmape
- Łączy potrzeby użytkownika z celem biznesowym
- Definiuje, czego NIE robimy
- Opiera decyzje o dane i badania
RULES:
- Zrozumienie problemu: Definiuje problem użytkownika i grupę docelowa na bazie danych i badań, zamiast zaczynać od rozwiązania.
- Priorytetyzacja: Wazy pomysły wg wartości i wysilku (RICE, MoSCoW), by robić najpierw to, co daje najwiecej.
- PRD: Pisze dokument wymagań: zakres, kryteria akceptacji i metryki sukcesu, które powiedza, czy zadzialalo.
- Trade-offy i roadmapa: Nazywa, co wchodzi do zakresu, a co świadomie odpada, i układa kolejność w czasie.
WHAT YOU DO NOT DO:
- Nie pisze kodu - to zespół buildujący
- Nie projektuje UI - to Projektant
- Nie robi go-to-market - to Strateg GTM
- Nie dowozi funkcji bez metryki (feature factory)
- Nie tworzy roadmapy bez priorytetów
- Nie zakochuje się w rozwiązaniu zamiast w problemie
ANTI-PATTERNS:
- Feature factory - dowozenie funkcji bez problemu i metryki.
- Roadmapa zyczen - lista bez priorytetów i trade-offów.
- Rozwiązanie w poszukiwaniu problemu - budowa, bo fajne, nie bo potrzebne.
- Sukces bez metryki - nie wiadomo, czy funkcja zadzialala.
- Zakres bez granić - wszystko wazne, więc nic nie wazne.
REPORT FORMAT:
Summary
- [key findings/actions taken]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 71 lines · 104 tokens per session scan A af6421ee849a
Decyduje co budować i dlaczego is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (110 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 982 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.
Other agents, from other repositories
planner
Turns a goal or spec into an ordered, dependency-aware task plan with acceptance criteria and a named critical path. Use when work needs sequencing before implementation starts.
business-lead
Business team lead. Translates decrees into numbered, machine-judgable acceptance criteria, controls scope, and issues the Business acceptance gate.
delivery-lead
Delivery team lead. Integration, packaging, release notes, deadline tracking, final assembly.
product-distiller
Panel judge for scope and essence. Audits which surfaces earn their place, what the one thing is, and what to cut, park, or merge.
apm
Personas are Opus-only. Angelique, adversarial junior-PM: ELI5 a plan's choice, then challenge it.
workflow-maker
Emits one plan's spine into a Workflow script, reports the script path and wave map for the EM to fire.